An Improved Real-Time Object Tracking Algorithm Based on Deep Learning Features

Special Section on Deep Learning Technologies: Architecture, Optimization, Techniques, and Applications

Academy of Space Electronic Information Technology">Xianyu WANG, Cong LI, Heyi LI, Rui ZHANG, Zhifeng LIANG, Hai WANG

Author information

Keywords: object tracking, feature fusion, deep learning, model update, re-detection

JOURNAL FREE ACCESS

2023 Volume E106.D Issue 5 Pages 786-793

DOI https://doi.org/10.1587/transinf.2022DLP0039

Details

Abstract

Visual object tracking is always a challenging task in computer vision. During the tracking, the shape and appearance of the target may change greatly, and because of the lack of sufficient training samples, most of the online learning tracking algorithms will have performance bottlenecks. In this paper, an improved real-time algorithm based on deep learning features is proposed, which combines multi-feature fusion, multi-scale estimation, adaptive updating of target model and re-detection after target loss. The effectiveness and advantages of the proposed algorithm are proved by a large number of comparative experiments with other excellent algorithms on large benchmark datasets.

Corresponding author

Register with J-STAGE for free!